Instructions to use head-empty-ai/Codename-Omega-Test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use head-empty-ai/Codename-Omega-Test with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="head-empty-ai/Codename-Omega-Test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("head-empty-ai/Codename-Omega-Test")
model = AutoModelForCausalLM.from_pretrained("head-empty-ai/Codename-Omega-Test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use head-empty-ai/Codename-Omega-Test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "head-empty-ai/Codename-Omega-Test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "head-empty-ai/Codename-Omega-Test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/head-empty-ai/Codename-Omega-Test

SGLang

How to use head-empty-ai/Codename-Omega-Test with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "head-empty-ai/Codename-Omega-Test" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "head-empty-ai/Codename-Omega-Test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "head-empty-ai/Codename-Omega-Test" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "head-empty-ai/Codename-Omega-Test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use head-empty-ai/Codename-Omega-Test with Docker Model Runner:
```
docker model run hf.co/head-empty-ai/Codename-Omega-Test
```

Codename-Omega-Test

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: NeverSleep/X-NoroChronos-13B
      layer_range: [0, 8]
  - sources:
    - model: Undi95/MLewdBoros-L2-13B
      layer_range: [8, 16]
  - sources:
    - model: NeverSleep/X-NoroChronos-13B
      layer_range: [16, 24]
  - sources:
    - model: Undi95/MLewdBoros-L2-13B
      layer_range: [24, 32]
  - sources:
    - model: Undi95/MythoMax-L2-Kimiko-v2-13b
      layer_range: [32, 40]
merge_method: passthrough
dtype: float16

Downloads last month: 9

Safetensors

Model size

13B params

Tensor type

F16

Model tree for head-empty-ai/Codename-Omega-Test

NeverSleep/X-NoroChronos-13B

Undi95/MLewdBoros-L2-13B

Undi95/MythoMax-L2-Kimiko-v2-13b

Merge model

this model